Factored Mllr Adaptation for Hmm-based Expressive Speech Synthesis

One of the most popular approaches to parameter adaptation in hidden Markov model (HMM) based systems is the maximum likelihood linear regression (MLLR) technique. In our previous work, we proposed factored MLLR (FMLLR) where MLLR parameter is defined as a function of a control parameter vector. We presented a method to train the FMLLR parameters based on a general framework of the expectationmaximization (EM) algorithm. To show the effectiveness, we applied the FMLLR to adapt the spectral envelope feature of the reading-style speech to those of the singing voice. In this paper, we apply the FMLLR to HMM-based expressive speech synthesis task and compare its performance with conventional approaches. In a series of experimental result, the FMLLR shows better performance than conventional methods.